Update README.md

README.md

@@ -16,7 +16,7 @@ tags:
 
 # CenterPoint on Axera NPU
 
-This repository contains the [CenterPoint](https://arxiv.org/abs/2006.11275) model converted for high-performance inference on the Axera NPU. CenterPoint is a center-based framework for 3D object detection and tracking that represents objects as points, significantly simplifying the detection pipeline while achieving state-of-the-art performance on LiDAR point clouds.
+This repository contains the [CenterPoint](https://arxiv.org/abs/2006.11275) model converted for high-performance inference on the Axera NPU. CenterPoint is a center-based framework for 3D object detection and tracking that represents objects as points, significantly simplifying the detection pipeline on LiDAR point clouds.
 
 This version is optimized with **w8a16** quantization and is compatible with **Pulsar2 version 4.2**.
 
@@ -32,13 +32,22 @@ For model conversion and deployment guidance:
   - [M4N-Dock (爱芯派Pro)](https://wiki.sipeed.com/hardware/zh/maixIV/m4ndock/m4ndock.html)
   - [M.2 Accelerator card](https://axcl-docs.readthedocs.io/zh-cn/latest/doc_guide_hardware.html)
 
-| Chips | Model Variant  | NPU3 Latency (Per Frame) |
-|---|---|---|---|
-| AX650 | CenterPoint-Pillar |  TBD |
+| Chips | Model Variant  | NPU3 Latency (ms) |
+|---|---|---|
+| AX650 | CenterPoint-Pillar |  88.334 |
 
 ## How to Use
 
-CenterPoint requires 3D point cloud inputs (typically LiDAR data in `.bin` or `.pcd` format).
+Download the repository and ensure the directory structure is organized as follows:
+
+```text
+.
+├── centerpoint.axmodel       # The compiled Axera model
+├── inference_axmodel.py      # Main inference script
+└── inference_data/           # Input directory
+    ├── config/               # Configuration files (e.g., inference_config.json)
+    └── data/                 # Data files (LiDAR point clouds)
+
 
 ### Prerequisites
 
@@ -53,7 +62,8 @@ CenterPoint requires 3D point cloud inputs (typically LiDAR data in `.bin` or `.
 Run the inference script by providing the compiled model, configuration, and data directory.
 
 ```bash
-python inference_axmodel.py compiled.axmodel inference_config.json inference_data/ --output-dir inference_results
+python inference_axmodel.py centerpoint.axmodel inference_data/config/inference_config.json inference_data/data/ --output-dir inference_results
+
 ```
 
 ### Inference with AX650 Host